Corpus ID: 43929379

VisualBackProp for learning using privileged information with CNNs

  title={VisualBackProp for learning using privileged information with CNNs},
  author={Devansh Bisla and A. Choromańska},
In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of learning algorithms and incorporate `physical,' `domain knowledge,' or `common sense' concepts into training of machine learning systems as well as verify constraints/properties of the systems. We explore the learning using privileged information paradigm and show how to incorporate the privileged information, such as… Expand
Leveraging Privileged Information to Limit Distraction in End-to-End Lane Following
This work investigates the use of Privileged Information for training an end-to-end lane following model and uses a pretrained lane segmentation model without fine-tuning to extract lane marking masks and shows that valuable learning signals can be extracted even from imperfect privileged knowledge. Expand
Learning the implicit strain reconstruction in ultrasound elastography using privileged information
This work is the first to develop an implicit strain reconstruction framework by a deep neural network architecture that proposes the learning-using-privileged-information (LUPI) paradigm with causality in the network to correct the intermediate state of the learning process. Expand


Training Group Orthogonal Neural Networks with Privileged Information
A novel group orthogonal convolutional neural network (GoCNN) that learns untangled representations within each layer by exploiting provided privileged information and enhances representation diversity effectively is proposed. Expand
VisualBackProp: visualizing CNNs for autonomous driving
The empirical evaluation shows the plausibility of the proposed approach on the road video data and reveals that it compares favorably to the LRP approach, i.e. it obtains similar visualization results and simultaneously achieves order of magnitude speed-ups. Expand
Visualizing and Understanding Convolutional Networks
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. Expand
Evaluating the Visualization of What a Deep Neural Network Has Learned
A general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps and shows that the recently proposed layer-wise relevance propagation algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method. Expand
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers by introducing a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. Expand
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets), and establishes the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks. Expand
Object Localization based on Structural SVM using Privileged Information
This work tackles object localization problem based on a novel structural SVM using privileged information, where an alternating loss-augmented inference procedure is employed to handle the term in the objective function corresponding to privileged information. Expand
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
This paper extends the LRP framework for Layer-wise Relevance Propagation for Fisher vector classifiers and uses it as analysis tool to quantify the importance of context for classification, qualitatively compare DNNs against FV classifiers in terms of important image regions and detect potential flaws and biases in data. Expand
Explaining Predictions of Non-Linear Classifiers in NLP
This paper applies layer-wise relevance propagation for the first time to natural language processing (NLP) and uses it to explain the predictions of a convolutional neural network trained on a topic categorization task. Expand
End to End Learning for Self-Driving Cars
A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems. Expand